pushing model

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Breakout-v5
     metrics:
     - type: mean_reward
-      value: 1.50 +/- 0.92
+      value: 2.30 +/- 1.90
       name: mean_reward
       verified: false
 ---
@@ -46,7 +46,7 @@ curl -OL https://huggingface.co/vwxyzjn/Breakout-v5-cleanba_ppo_envpool_impala_a
 curl -OL https://huggingface.co/vwxyzjn/Breakout-v5-cleanba_ppo_envpool_impala_atari_wrapper_naturecnn-seed1/raw/main/pyproject.toml
 curl -OL https://huggingface.co/vwxyzjn/Breakout-v5-cleanba_ppo_envpool_impala_atari_wrapper_naturecnn-seed1/raw/main/poetry.lock
 poetry install --all-extras
-python cleanba_ppo_envpool_impala_atari_wrapper_naturecnn.py --total-timesteps 200000 --distributed --learner-device-ids 1 --track --save-model --upload-model --env-id Breakout-v5 --seed 1
+python cleanba_ppo_envpool_impala_atari_wrapper_naturecnn.py --total-timesteps 200000 --distributed --track --save-model --upload-model --env-id Breakout-v5 --seed 1
 ```
 
 # Hyperparameters
@@ -66,10 +66,10 @@ python cleanba_ppo_envpool_impala_atari_wrapper_naturecnn.py --total-timesteps 2
  'exp_name': 'cleanba_ppo_envpool_impala_atari_wrapper_naturecnn',
  'gae_lambda': 0.95,
  'gamma': 0.99,
- 'global_learner_decices': ['gpu:1', 'gpu:3'],
+ 'global_learner_decices': ['gpu:0', 'gpu:1'],
  'hf_entity': '',
- 'learner_device_ids': [1],
- 'learner_devices': ['gpu:1'],
+ 'learner_device_ids': [0],
+ 'learner_devices': ['gpu:0'],
  'learning_rate': 0.00025,
  'local_batch_size': 7680,
  'local_minibatch_size': 1920,

cleanba_ppo_envpool_impala_atari_wrapper_naturecnn.cleanrl_model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e11c4688da03104f3b888acdeb3d20ca2833bcd4cd23f7fa13f4d22395614f17
+oid sha256:750ba5b5633deae0dd6920a0c7f237887c2de96f04bcc577fed6be8488766d0e
 size 6747982